© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 6530
    Prev
    Next
    INDEX
    Explanations

    references to social and political issues affecting marginalized communities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.05
    1:0.06
    2:0.05
    3:0.05
    4:0.12
    5:0.02
    6:0.14
    7:0.23
    8:0.02
    9:0.03
    10:0.03
    11:0.14
    Negative Logits
    Room
    -2.16
    ixtures
    -2.15
    ンジ
    -1.95
    ramids
    -1.94
     intercepted
    -1.90
     simulate
    -1.88
    HS
    -1.88
     Rooms
    -1.87
     preparations
    -1.87
    acting
    -1.86
    POSITIVE LOGITS
     Issue
    3.63
    Issue
    3.62
     issue
    3.47
    issue
    3.15
    Iss
    3.15
     issues
    2.88
     Issues
    2.64
    issues
    2.58
    Reviewer
    2.48
     answ
    2.29
    Activations Density 0.062%

    No Known Activations